Artificial intelligence in infection prevention and control education: toward intelligent, real-time clinical learning systems

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Artificial intelligence (AI) is increasingly being explored in infection prevention and control (IPC) education as a means of addressing limitations of conventional training, including limited scalability, delayed feedback, and subjective competency assessment. This mini review summarizes emerging applications of AI-enabled technologies in IPC education and examines their potential educational benefits, limitations, and implementation considerations. Current evidence includes applications of computer vision for behavioral assessment, AI-integrated virtual and extended reality for immersive and adaptive learning, and large language models for knowledge support and interactive learning. Available studies suggest that AI-assisted interventions may improve procedural performance, learner engagement, feedback efficiency, and selected measures of knowledge or self-efficacy. However, the evidence remains heterogeneous, with substantial variation in AI modalities, learner populations, study designs, outcome measures, and follow-up periods. Many studies are based on small samples or single-center settings and primarily evaluate short-term educational outcomes, limiting conclusions regarding sustained competency acquisition or translation into clinical practice. Evidence linking AI-assisted IPC education to reductions in healthcare-associated infections remains particularly limited. Important challenges also include workforce readiness, infrastructure and interoperability, privacy and governance, and potential cognitive burden associated with immersive technologies. Overall, AI shows promise as an enabling component of adaptive, data-supported, and feedback-oriented IPC education, but its educational and clinical value requires further validation through larger, multicenter, longitudinal, and implementation-focused studies.